Latest news

View all

About the center

BCAM obtains funding for six projects through the PID 2024 CALL from the State Research Agency

This call is aimed at funding scientific research and knowledge advancement, both in non-oriented areas and in areas oriented towards solving specific problems.  BCAM has successfully obtained funding for six of its research projects through the prestigious PID 2024 (Proyectos de Generación de…

About the center

Book of Abstracts for ESGI 188 now available

  • The 188th European Study Group with Industry (ESGI 188), hosted from May 26 to 30 at Bilbao's B Accelerator Tower (BAT), has concluded with the release of its Book of Abstracts.

About the center

Researchers from BCAM, ARAYA INC., The University Of Sussex, and The University Of Kyoto develop a new class of Artificial Intelligence models called CURVED NEURAL NETWORKS

  •  What if Artificial Intelligence could remember things not just well, but faster or more reliably?

BCAM people

BCAM’s postdoctoral researcher Verónica Álvarez Castro, awarded as one of the Young Researchers in Computer Science in the The Research Awards of the Scientific Society of Computer Science of Spain (SCIE )-Fundación BBVA

  • The jury of these awards has taken into account her contributions to machine learning in the field of adaptation to temporal changes, both in its mo

Latest publications

View all

Transforming Combinatorial Optimization Problems in Fourier Space: Consequences and Uses

Elorza, A.; Benavides, X.; Ceberio, J.; Hernando, L.; Lozano, J.A. (2024-09-10)

We analyze three permutation-based combinatorial optimization problems in Fourier space, namely, the quadratic assignment problem, the linear ordering problem (LOP), and the symmetric and nonsymmetric traveling salesperson p...

Learning the Graph Structure of Regular Vine-Copulas from Dependence Lists

Carrera, D.; Santana, R.; Lozano, J.A. (2025-01-01)

Regular vine copulas (R-vines) provide a comprehensive framework for modeling high- dimensional dependencies using a hierarchy of trees and conditional pair-copulas. While the graphical structure of R-vines is traditionall...

Self-Composing Policies for Scalable Continual Reinforcement Learning

Vadillo, J.; Santana, R.; Lozano, J.A. (2025-01-01)

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness again...

Self-Composing Policies for Scalable Continual Reinforcement Learning

Malagon, M.; Ceberio, J.; Lozano, J.A. (2025-01-01)

This work introduces a growable and modular neural network architecture that naturally avoids catastrophic forgetting and interference in con- tinual reinforcement learning. The structure of each module allows the select...